7 papers
Multi-domain semantic segmentation with overlapping labels
Petra Bevandić, Marin Oršić, Ivan Grubišić +2
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degr…
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications. One of the major unsolved problems is to identi…
Single Level Feature-to-Feature Forecasting with Deformable Convolutions
Josip Šarić, Marin Oršić, Tonći Antunović +2
Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driv…
Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings
Borna Bićanić, Marin Oršić, Ivan Marković +2
This paper studies the interplay between kinematics (position and velocity) and appearance cues for establishing correspondences in multi-target pedestrian tracking. We investigate…
In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
Marin Oršić, Ivan Krešo, Petra Bevandić +1
Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve re…
Discriminative out-of-distribution detection for semantic segmentation
Petra Bevandić, Ivan Krešo, Marin Oršić +1
Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However,…